|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* @file |
|
5
|
|
|
* This file is part of the PdfParser library. |
|
6
|
|
|
* |
|
7
|
|
|
* @author Sébastien MALOT <[email protected]> |
|
8
|
|
|
* |
|
9
|
|
|
* @date 2017-01-03 |
|
10
|
|
|
* |
|
11
|
|
|
* @license LGPLv3 |
|
12
|
|
|
* |
|
13
|
|
|
* @url <https://github.com/smalot/pdfparser> |
|
14
|
|
|
* |
|
15
|
|
|
* PdfParser is a pdf library written in PHP, extraction oriented. |
|
16
|
|
|
* Copyright (C) 2017 - Sébastien MALOT <[email protected]> |
|
17
|
|
|
* |
|
18
|
|
|
* This program is free software: you can redistribute it and/or modify |
|
19
|
|
|
* it under the terms of the GNU Lesser General Public License as published by |
|
20
|
|
|
* the Free Software Foundation, either version 3 of the License, or |
|
21
|
|
|
* (at your option) any later version. |
|
22
|
|
|
* |
|
23
|
|
|
* This program is distributed in the hope that it will be useful, |
|
24
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
25
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
26
|
|
|
* GNU Lesser General Public License for more details. |
|
27
|
|
|
* |
|
28
|
|
|
* You should have received a copy of the GNU Lesser General Public License |
|
29
|
|
|
* along with this program. |
|
30
|
|
|
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>. |
|
31
|
|
|
*/ |
|
32
|
|
|
|
|
33
|
|
|
namespace Smalot\PdfParser; |
|
34
|
|
|
|
|
35
|
|
|
use Smalot\PdfParser\Element\ElementArray; |
|
36
|
|
|
use Smalot\PdfParser\Element\ElementMissing; |
|
37
|
|
|
use Smalot\PdfParser\Element\ElementStruct; |
|
38
|
|
|
use Smalot\PdfParser\Element\ElementXRef; |
|
39
|
|
|
|
|
40
|
|
|
/** |
|
41
|
|
|
* Class Header |
|
42
|
|
|
*/ |
|
43
|
|
|
class Header |
|
44
|
|
|
{ |
|
45
|
|
|
/** |
|
46
|
|
|
* @var Document|null |
|
47
|
|
|
*/ |
|
48
|
|
|
protected $document; |
|
49
|
|
|
|
|
50
|
|
|
/** |
|
51
|
|
|
* @var Element[] |
|
52
|
|
|
*/ |
|
53
|
|
|
protected $elements; |
|
54
|
|
|
|
|
55
|
|
|
/** |
|
56
|
|
|
* @param Element[] $elements list of elements |
|
57
|
|
|
* @param Document $document document |
|
58
|
|
|
*/ |
|
59
|
103 |
|
public function __construct(array $elements = [], ?Document $document = null) |
|
60
|
|
|
{ |
|
61
|
103 |
|
$this->elements = $elements; |
|
62
|
103 |
|
$this->document = $document; |
|
63
|
|
|
} |
|
64
|
|
|
|
|
65
|
73 |
|
public function init() |
|
66
|
|
|
{ |
|
67
|
73 |
|
foreach ($this->elements as $element) { |
|
68
|
73 |
|
if ($element instanceof Element) { |
|
69
|
72 |
|
$element->init(); |
|
70
|
|
|
} |
|
71
|
|
|
} |
|
72
|
|
|
} |
|
73
|
|
|
|
|
74
|
|
|
/** |
|
75
|
|
|
* Returns all elements. |
|
76
|
|
|
*/ |
|
77
|
66 |
|
public function getElements() |
|
78
|
|
|
{ |
|
79
|
66 |
|
foreach ($this->elements as $name => $element) { |
|
80
|
66 |
|
$this->resolveXRef($name); |
|
81
|
|
|
} |
|
82
|
|
|
|
|
83
|
66 |
|
return $this->elements; |
|
84
|
|
|
} |
|
85
|
|
|
|
|
86
|
|
|
/** |
|
87
|
|
|
* Used only for debug. |
|
88
|
|
|
*/ |
|
89
|
1 |
|
public function getElementTypes(): array |
|
90
|
|
|
{ |
|
91
|
1 |
|
$types = []; |
|
92
|
|
|
|
|
93
|
1 |
|
foreach ($this->elements as $key => $element) { |
|
94
|
1 |
|
$types[$key] = \get_class($element); |
|
95
|
|
|
} |
|
96
|
|
|
|
|
97
|
1 |
|
return $types; |
|
98
|
|
|
} |
|
99
|
|
|
|
|
100
|
61 |
|
public function getDetails(bool $deep = true): array |
|
101
|
|
|
{ |
|
102
|
61 |
|
$values = []; |
|
103
|
61 |
|
$elements = $this->getElements(); |
|
104
|
|
|
|
|
105
|
61 |
|
foreach ($elements as $key => $element) { |
|
106
|
61 |
|
if ($element instanceof self && $deep) { |
|
107
|
|
|
$values[$key] = $element->getDetails($deep); |
|
108
|
61 |
|
} elseif ($element instanceof PDFObject && $deep) { |
|
109
|
3 |
|
$values[$key] = $element->getDetails(false); |
|
110
|
61 |
|
} elseif ($element instanceof ElementArray) { |
|
111
|
3 |
|
if ($deep) { |
|
112
|
3 |
|
$values[$key] = $element->getDetails(); |
|
113
|
|
|
} |
|
114
|
61 |
|
} elseif ($element instanceof Element) { |
|
115
|
61 |
|
$values[$key] = (string) $element; |
|
116
|
|
|
} |
|
117
|
|
|
} |
|
118
|
|
|
|
|
119
|
61 |
|
return $values; |
|
120
|
|
|
} |
|
121
|
|
|
|
|
122
|
|
|
/** |
|
123
|
|
|
* Indicate if an element name is available in header. |
|
124
|
|
|
* |
|
125
|
|
|
* @param string $name the name of the element |
|
126
|
|
|
*/ |
|
127
|
78 |
|
public function has(string $name): bool |
|
128
|
|
|
{ |
|
129
|
78 |
|
return \array_key_exists($name, $this->elements); |
|
130
|
|
|
} |
|
131
|
|
|
|
|
132
|
|
|
/** |
|
133
|
|
|
* @return Element|PDFObject |
|
134
|
|
|
*/ |
|
135
|
80 |
|
public function get(string $name) |
|
136
|
|
|
{ |
|
137
|
80 |
|
if (\array_key_exists($name, $this->elements) && $element = $this->resolveXRef($name)) { |
|
138
|
79 |
|
return $element; |
|
139
|
|
|
} |
|
140
|
|
|
|
|
141
|
76 |
|
return new ElementMissing(); |
|
142
|
|
|
} |
|
143
|
|
|
|
|
144
|
|
|
/** |
|
145
|
|
|
* Resolve XRef to object. |
|
146
|
|
|
* |
|
147
|
|
|
* @return Element|PDFObject |
|
148
|
|
|
* |
|
149
|
|
|
* @throws \Exception |
|
150
|
|
|
*/ |
|
151
|
81 |
|
protected function resolveXRef(string $name) |
|
152
|
|
|
{ |
|
153
|
81 |
|
if (($obj = $this->elements[$name]) instanceof ElementXRef && null !== $this->document) { |
|
154
|
|
|
/** @var ElementXRef $obj */ |
|
155
|
67 |
|
$object = $this->document->getObjectById($obj->getId()); |
|
156
|
|
|
|
|
157
|
67 |
|
if (null === $object) { |
|
158
|
2 |
|
return new ElementMissing(); |
|
159
|
|
|
} |
|
160
|
|
|
|
|
161
|
|
|
// Update elements list for future calls. |
|
162
|
67 |
|
$this->elements[$name] = $object; |
|
163
|
|
|
} |
|
164
|
|
|
|
|
165
|
81 |
|
return $this->elements[$name]; |
|
166
|
|
|
} |
|
167
|
|
|
|
|
168
|
|
|
/** |
|
169
|
|
|
* @param string $content The content to parse |
|
170
|
|
|
* @param Document $document The document |
|
171
|
|
|
* @param int $position The new position of the cursor after parsing |
|
172
|
|
|
*/ |
|
173
|
29 |
|
public static function parse(string $content, Document $document, int &$position = 0): self |
|
174
|
|
|
{ |
|
175
|
|
|
/* @var Header $header */ |
|
176
|
29 |
|
if ('<<' == substr(trim($content), 0, 2)) { |
|
177
|
28 |
|
$header = ElementStruct::parse($content, $document, $position); |
|
178
|
|
|
} else { |
|
179
|
15 |
|
$elements = ElementArray::parse($content, $document, $position); |
|
180
|
15 |
|
$header = new self([], $document); |
|
181
|
|
|
|
|
182
|
15 |
|
if ($elements) { |
|
183
|
14 |
|
$header = new self($elements->getRawContent(), null); |
|
184
|
|
|
} |
|
185
|
|
|
} |
|
186
|
|
|
|
|
187
|
29 |
|
if ($header) { |
|
188
|
29 |
|
return $header; |
|
189
|
|
|
} |
|
190
|
|
|
|
|
191
|
|
|
// Build an empty header. |
|
192
|
|
|
return new self([], $document); |
|
193
|
|
|
} |
|
194
|
|
|
} |
|
195
|
|
|
|
smalot /
pdfparser
